Top explainable-ai open source projects

Predictive AI layer for existing databases.

✭ 4,199

python hacktoberfest machine-learning pytorch mysql artificial-intelligence ml automl mariadb clickhouse postgresql snowflake machine-learning-api explainable-ai explainable-ml singlestore

Interpret

Fit interpretable models. Explain blackbox machine learning.

Tensorwatch

Debugging, monitoring and visualization for Python Machine Learning and Data Science

✭ 3,191

python Jupyter Notebook jupyter-notebook deep-learning machine-learning data-science monitoring reinforcement-learning ai deeplearning jupyter debugging debug machinelearning debugging-tool saliency explainable-ai explainable-ml model-visualization

ml-fairness-framework

FairPut - Machine Learning Fairness Framework with LightGBM — Explainability, Robustness, Fairness (by @firmai)

✭ 59

Jupyter Notebook contrastive counterfactual explainable-ai explainable-ml xai interpretable-machine-learning fairness-ai aif360 fairness-ml alibi prototypical aix360 fairness-indicators

WhiteBox-Part1

In this part, I've introduced and experimented with ways to interpret and evaluate models in the field of image. (Pytorch)

✭ 34

Jupyter Notebook machine-learning computer-vision deep-learning grad-cam mnist gradients backpropagation blackbox saliency-map cifar-10 smoothgrad guided-backpropagation interpretable-ai explainable-ai integrated-gradients evaluate-models

global-attribution-mapping

GAM (Global Attribution Mapping) explains the landscape of neural network predictions across subpopulations

✭ 18

python Makefile neural-networks explainable-ai explainable-ml

SHAP FOLD

(Explainable AI) - Learning Non-Monotonic Logic Programs From Statistical Models Using High-Utility Itemset Mining

✭ 35

prolog Jupyter Notebook HTML java python machine-learning data-mining inductive-logic-programming explainable-ai explainable-ml rule-induction

fastshap

Fast approximate Shapley values in R

✭ 79

r C++variable-importance explainable-ai explainable-ml xai shapley interpretable-machine-learning shapley-values

shapr

Explaining the output of machine learning models with more accurately estimated Shapley values

✭ 95

r C++TeX python rcpp rstats rcpparmadillo explainable-ai explainable-ml shapley

CARLA

CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

✭ 166

python Jupyter Notebook Makefile benchmarking benchmark machine-learning tensorflow pytorch artificial-intelligence counterfactual explainable-ai explainable-ml explainability tensorflow2 counterfactual-explanations counterfactuals recourse

awesome-graph-explainability-papers

Papers about explainability of GNNs

✭ 153

machine-learning deep-learning graph-mining explainable-ai xai graph-neural-networks explainability

path explain

A repository for explaining feature attributions and feature interactions in deep neural networks.

✭ 151

Jupyter Notebook python shell machine-learning tensorflow pytorch interpretable-deep-learning explainable-ai

ddsm-visual-primitives

Using deep learning to discover interpretable representations for mammogram classification and explanation

✭ 25

Jupyter Notebook python deep-learning cnn pytorch convolutional-neural-networks mammogram explainable-ai expert-in-the-loop ddsm mammography

GraphLIME

This is a Pytorch implementation of GraphLIME

✭ 40

Jupyter Notebook python shell open-source graph-algorithms explainable-ai graph-neural-networks

zennit

Zennit is a high-level framework in Python using PyTorch for explaining/exploring neural networks using attribution methods like LRP.

✭ 57

python shell machine-learning deep-learning attribution pytorch interpretability interpretable-ai interpretable-ml explainable-ai xai lrp explainability feature-attribution

Relevance-CAM

The official code of Relevance-CAM

✭ 21

python explainable-ai class-activation-map relevance-cam

ProtoTree

ProtoTrees: Neural Prototype Trees for Interpretable Fine-grained Image Recognition, published at CVPR2021

✭ 47

python deep-neural-networks computer-vision pytorch decision-trees interpretability fine-grained-classification interpretable-deep-learning explainable-ai explainable-ml interpretable-machine-learning fine-grained-visual-categorization explainability cvpr2021

ShapleyExplanationNetworks

Implementation of the paper "Shapley Explanation Networks"

✭ 62

python machine-learning deep-learning interpretable-deep-learning explainable-ai interpretable-machine-learning iclr2021

awesome-agi-cocosci

An awesome & curated list for Artificial General Intelligence, an emerging inter-discipline field that combines artificial intelligence and computational cognitive sciences.

javaAnchorExplainer

Explains machine learning models fast using the Anchor algorithm originally proposed by marcotcr in 2018

✭ 17

java machine-learning algorithm ai anchor h2oai explainable-ai

Awesome-Vision-Transformer-Collection

Variants of Vision Transformer and its downstream tasks

✭ 124

tracking awesome computer-vision deep-learning detection backbone generative-model segmentation pose-estimation lidar-point-cloud explainable-ai self-attention self-supervised-learning

deep-explanation-penalization

Code for using CDEP from the paper "Interpretations are useful: penalizing explanations to align neural networks with prior knowledge" https://arxiv.org/abs/1909.13584

Relational Deep Reinforcement Learning

No description or website provided.

✭ 44

python reinforcement-learning tensorflow relational-networks proximal-policy-optimization ppo explainable-ai self-attention

fast-tsetlin-machine-with-mnist-demo

A fast Tsetlin Machine implementation employing bit-wise operators, with MNIST demo.

✭ 58

c Makefile machine-learning artificial-intelligence mnist pattern-recognition bitwise-operators frequent-pattern-mining rule-based explainable-ai tsetlin-machine

transformers-interpret

Model explainability that works seamlessly with 🤗 transformers. Explain your transformers model in just 2 lines of code.

✭ 861

Jupyter Notebook python nlp machine-learning natural-language-processing computer-vision deep-learning neural-network transformers interpretability explainable-ai captum model-explainability transformers-model

mllp

The code of AAAI 2020 paper "Transparent Classification with Multilayer Logical Perceptrons and Random Binarization".

✭ 15

python Jupyter Notebook machine-learning transparency aaai interpretability rule-based interpretable-ai interpretable-ml explainable-ai explainable-ml xai interpretable-machine-learning iml machine-learning-interpretability explainability rule-sets interpretml transparent-ml

responsible-ai-toolbox

This project provides responsible AI user interfaces for Fairlearn, interpret-community, and Error Analysis, as well as foundational building blocks that they rely on.

hierarchical-dnn-interpretations

Using / reproducing ACD from the paper "Hierarchical interpretations for neural network predictions" 🧠 (ICLR 2019)

meg

Molecular Explanation Generator

✭ 14

python shell reinforcement-learning interpretability explainable-ai counterfactual-explanations deep-graph-networks deep-learning-for-graphs

dlime experiments

In this work, we propose a deterministic version of Local Interpretable Model Agnostic Explanations (LIME) and the experimental results on three different medical datasets shows the superiority for Deterministic Local Interpretable Model-Agnostic Explanations (DLIME).

✭ 21

Jupyter Notebook python machine-learning random-forest scikit-learn neural-networks clusters knn lime classifiers explainable-ai explainable-ml xai heirarchical-clustering breast-cancer-dataset dlime

Transformer-MM-Explainability

[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-based network. Including examples for DETR, VQA.

✭ 484

Jupyter Notebook python javascript shell c CSS visualization transformers transformer vqa clip interpretability explainable-ai explainability detr lxmert visualbert

concept-based-xai

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

✭ 41

python shell library weak-supervision vae concept concept-extraction weakly-supervised-learning interpretability disentanglement model-explanation explainable-ai disentangled-representations xai explainability concept-explanation

bert attn viz

Visualize BERT's self-attention layers on text classification tasks

✭ 41

python Jupyter Notebook nlp tensorflow attention bert explainable-ai

DataScience ArtificialIntelligence Utils

Examples of Data Science projects and Artificial Intelligence use cases

✭ 302

Jupyter Notebook python data-science machine-learning natural-language-processing reinforcement-learning computer-vision deep-learning time-series examples regression data-visualization artificial-intelligence classification explainable-ai explainable-ml

expmrc

ExpMRC: Explainability Evaluation for Machine Reading Comprehension

✭ 58

python nlp dataset question-answering machine-reading-comprehension explainable-ai xai expmrc cmrc2022

3D-GuidedGradCAM-for-Medical-Imaging

This Repo containes the implemnetation of generating Guided-GradCAM for 3D medical Imaging using Nifti file in tensorflow 2.0. Different input files can be used in that case need to edit the input to the Guided-gradCAM model.

✭ 60